Hi Antonella,
I think that lme4 does not have yet corStruct classes available, at
least for the currect version for Windows which I have. So I'd suggest
you to use the nlme package.
I hope it helps.
Best,
Dimitris
----
Dimitris Rizopoulos
Ph.D. Student
Biostatistical Centre
School of Public Health
Catholic University of Leuven
Address: Kapucijnenvoer 35, Leuven, Belgium
Tel: +32/16/336899
Fax: +32/16/337015
Web: http://www.med.kuleuven.ac.be/biostat
http://www.student.kuleuven.ac.be/~m0390867/dimitris.htm
----- Original Message -----
From: "Antonella Plaia" <plaia at unipa.it>
To: <r-help at stat.math.ethz.ch>
Sent: Tuesday, December 14, 2004 2:57 PM
Subject: [R] correlation in lme4
> Dear all,
> I have tried to consider a correlation structure in lme (package
> lme4), but
> without success.
> I have used something like:
>
>> risul<-lme(y~x+ z , data=mydata, random=~ x | g, correlation =
>> corAR1())
>
> but the result is the same as:
>
>> risul<-lme(y~x+ z , data=mydata, random=~ x | g).
>
> Can anybody help me?
>
> Antonella
>
>
> **************************************************
> Prof. Antonella Plaia
> Dipartimento di Scienze Statistiche e Matematiche "S. Vianelli"
> Universit?? di Palermo
> Viale delle Scienze 90128 Palermo ITALIA
> Tel. +39 091 6626244 Fax +39 091 485726
> http://dssm.unipa.it/plaia
> e-mail:plaia at unipa.it
>
--------------------------------------------------------------------------------
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide!
> http://www.R-project.org/posting-guide.html